Merge pull request #230 from billd100/fix/age-restricted-videos-without-signature

pytube/__main__.py

@@ -109,7 +109,7 @@ class YouTube(object):
             self.player_config_args = self.vid_info
         else:
             self.player_config_args = extract.get_ytplayer_config(
-                self.watch_html,
+                self.watch_html
             )['args']
 
         # https://github.com/nficano/pytube/issues/165
@@ -123,8 +123,13 @@ class YouTube(object):
                 mixins.apply_descrambler(self.vid_info, fmt)
             mixins.apply_descrambler(self.player_config_args, fmt)
 
-            # apply the signature to the download url.
-            mixins.apply_signature(self.player_config_args, fmt, self.js)
+            try:
+                mixins.apply_signature(self.player_config_args, fmt, self.js)
+            except TypeError:
+                self.js_url = extract.js_url(
+                    self.embed_html, self.age_restricted)
+                self.js = request.get(self.js_url)
+                mixins.apply_signature(self.player_config_args, fmt, self.js)
 
             # build instances of :class:`Stream <Stream>`
             self.initialize_stream_objects(fmt)
@@ -157,7 +162,7 @@ class YouTube(object):
         )
         self.vid_info = request.get(self.vid_info_url)
         if not self.age_restricted:
-            self.js_url = extract.js_url(self.watch_html)
+            self.js_url = extract.js_url(self.watch_html, self.age_restricted)
             self.js = request.get(self.js_url)
 
     def initialize_stream_objects(self, fmt):

pytube/extract.py

@@ -111,7 +111,7 @@ def video_info_url(
     return 'https://youtube.com/get_video_info?' + urlencode(params)
 
 
-def js_url(watch_html):
+def js_url(html, age_restricted=False):
     """Get the base JavaScript url.
 
     Construct the base JavaScript url, which contains the decipher
@@ -119,9 +119,11 @@ def js_url(watch_html):
 
     :param str watch_html:
         The html contents of the watch page.
+    :param bool age_restricted:
+        Is video age restricted.
 
     """
-    ytplayer_config = get_ytplayer_config(watch_html)
+    ytplayer_config = get_ytplayer_config(html, age_restricted)
     base_js = ytplayer_config['assets']['js']
     return 'https://youtube.com' + base_js
 
@@ -150,7 +152,7 @@ def mime_type_codec(mime_type_codec):
     return mime_type, [c.strip() for c in codecs.split(',')]
 
 
-def get_ytplayer_config(watch_html):
+def get_ytplayer_config(html, age_restricted=False):
     """Get the YouTube player configuration data from the watch html.
 
     Extract the ``ytplayer_config``, which is json data embedded within the
@@ -159,10 +161,15 @@ def get_ytplayer_config(watch_html):
 
     :param str watch_html:
         The html contents of the watch page.
+    :param bool age_restricted:
+        Is video age restricted.
     :rtype: str
     :returns:
         Substring of the html containing the encoded manifest data.
     """
-    pattern = r';ytplayer\.config\s*=\s*({.*?});'
-    yt_player_config = regex_search(pattern, watch_html, group=1)
+    if age_restricted:
+        pattern = r";yt\.setConfig\(\{'PLAYER_CONFIG':\s*({.*})(,'EXPERIMENT_FLAGS'|;)"  # noqa: E501
+    else:
+        pattern = r';ytplayer\.config\s*=\s*({.*?});'
+    yt_player_config = regex_search(pattern, html, group=1)
     return json.loads(yt_player_config)

pytube/mixins.py

@@ -33,11 +33,16 @@ def apply_signature(config_args, fmt, js):
         if 'signature=' in url:
             # For certain videos, YouTube will just provide them pre-signed, in
             # which case there's no real magic to download them and we can skip
-            # the whole signature decrambling entirely.
+            # the whole signature descrambling entirely.
             logger.debug('signature found, skip decipher')
             continue
 
-        signature = cipher.get_signature(js, stream['s'])
+        if js is not None:
+            signature = cipher.get_signature(js, stream['s'])
+        else:
+            # signature not present in url (line 33), need js to descramble
+            # TypeError caught in __main__
+            raise TypeError('JS is None')
 
         logger.debug(
             'finished descrambling signature for itag=%s\n%s',